© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84153
    Prev
    Next
    INDEX
    Explanations

    technical computing and science

    np_acts-logits-general · gemini-2.5-flash-lite

    technical terms related to distributed computing systems, particularly Hadoop and file systems.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron detects mentions of Hadoop‐ecosystem technical terms (e.g. “HDFS,” “Hadoop,” “Data locality,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     feliz
    -0.79
     متحده
    -0.76
    ější
    -0.75
    ֻ
    -0.75
     Þ
    -0.75
     audiences
    -0.75
    通販
    -0.74
    场
    -0.74
    BlockingQueue
    -0.73
    iosync
    -0.73
    POSITIVE LOGITS
    的说
    0.89
    豪华
    0.85
    客气
    0.78
     erasure
    0.76
     Nervous
    0.76
    Starter
    0.74
    čních
    0.72
     Eras
    0.71
    取代
    0.71
    对外
    0.70
    Activations Density 0.003%

    No Known Activations